Feature Extraction Run Length The main steps in the process of feature extraction is

Jurnal Ilmiah Komputer dan Informatika KOMPUTA Edisi...Volume..., Bulan 20..ISSN :2089-9033 Table 9 Probability Density Value Data Testing Then calculate the value of evidence and posterior Evidence = 0.25 x 0 x 0 x 0.0001 x 0 x 0 + 0.25 x 0 x 0 x 0 x 0 x 25.2196 + 0.25 x 0 x 0.0001 x 0 x 0 x 0.0361 + 0.25 x 21.2009 x 0.0138 x 0 x 0 x 0.1358 = 0.0000001 Posterior ALL = PALL . PSRE | ALL . PLRE | ALL. PGLU | ALL. PRLU | ALL. PRPC | ALL Evidence Posterior ALL =0.25 x 0 x 0 x 0.0001 x 0 x 0 0.0000001 = 1 Posterior AML = PAML . PSRE | AML . PLRE | AML. PGLU | AML. PRLU | AML. PRPC | AML Evidence Posterior AML = 0.25 x 0 x 0 x 0 x 0 x 25.2196 0.0000001 = 0 PosteriorCLL = PCLL . PSRE | CLL . PLRE | CLL. PGLU | CLL. PRLU | CLL. PRPC | CLL Evidence PosteriorCLL = 0.25 x 0 x 0.0001 x 0 x 0 x 0.0361 0.0000001 = 0 PosteriorCML = PCML . PSRE | CML . PLRE | CML. PGLU | CML. PRLU | CML. PRPC | CML Evidence PosteriorCML = 0.25 x 21.2009 x 0.0138 x 0 x 0 x 0.1358 0.0000001 = 0.000001

2.5 Implementation Interface Implementation Interface explain and describe the

implementation of each of the existing processes in this system: Picture 10 Display Main Menu Picture 11 Menu Display Processing Picture 12 Training Menu Display Picture 13 Display Menu Tests

3. CONCLUSION Based on the results of the testing that has been

done, it was concluded that the naïve Bayes method can classify the input image by statistical data directly comparing the closest distance to the training. Testing image classification based on the texture using image data that has been trained to have an average accuracy rate of 100 and for the Jurnal Ilmiah Komputer dan Informatika KOMPUTA Edisi...Volume..., Bulan 20..ISSN :2089-9033 image that has not been trained in the average accuracy rate of 90 and the level of accuracy using three training data is 85 and the use of four training data is 90 . From the results of the entire test, naïve Bayes algorithm produces 91.25 accuracy rate with a total of 20 training data and 20 test data. 4. BIBLIOGRAPHY [1] Rizkiana, U. 2009.“Penerimaan Diri Pada Remaja Penderita Leukemia”. Jurnal Psikologi Vol. 2 No. 2 : 114-122. Universitas Gunadarma, Depok. [2] Bharathivanan, A. 2015. “Local Binary Texture Based Method for Segmentation of Leukemia in Blood Microscopic Images”. Journal of Applied Engineering Research Vol. 10 No. 20 : 16291-16296. Valliammai Engineering College, India. [3] Praida, A, R. 2008. “Pengenalan Penyakit Darah Menggunakan Teknik Pengolahan Citra dan Jaringan Syaraf Tiruan”. Tugas Akhir Teknik Elektro . Universitas Indonesia, Depok. [4] Simon, Sumanto, dr. Sp. PK. 2003. “Neoplasma Sistem Hematopoietik: Leukemia”. Fakultas Kedokteran Unika Atma Jaya Jakarta.Sreenivasulu M, 2011, Performance Evaluation of EFCI and ERICA Schemes for ATM Networks ”. [5] Ahmad, U. 2005. “Pengolahan Citra Digital Teknik Pemrogramannya”. Yogyakarta: Graha Ilmu. [6] Galloway, M. 1975. “Texture Analysis Using Gray Level Run Length”. Computer Graphics Image Process vol. 4, pp. 172-179. [7] Prasetyo, E. 2012. “Pengenalan Pola Naïve Bayes”. Universitas Pembangunan Nasional. Jawa Timur. [8] Visa, S. 2011. “Confusion Matrix-Based Feature Selection”. Proceedings of the 22 nd Midwest Artficial Intelligence and Cognitive Science Conference : 120-127.